Land Cover/Land Use Classification of Urban Areas: A Remote Sensing Approach

摘要

We have proposed a system for remote sensing based land cover/land use classifi- cation of urban areas. The method permits using multichannel and multitemporal satellite data, and it can be easily adapted to the classification scheme at hand. The results reported have shown the potentials of the method to handle large num- Ber of land cover/land use classes by selecting with a new CART based feature Selection algorithm subsets of features from a high dimensional feature space which Consistently enabled us to achieve eventually good classification performances. The Described system should be of interest to the remote sensing community for many Of their tasks due to its easy adaptivity to different types of remotely sensed data And classification schemes.